Microsoft researchers worked with botanists at the Institute of Botany, Chinese Academy of Sciences (IBCAS) to developer the Smart Flower Recognition System can be used to recognize the type of flower from its image. At least 250,000 species of flowers exist and even experienced botanists have trouble identifying them all. Using MSRA’s image-recognition technology and 2.6 million images from IBCAS, researches used 20-layer convolutional neural network to recognize images using a set of learnable filters.
During the forward pass, each filter is convolved across the width and height of the input volume, computing the dot product between the entries of the filter and the input. This produces a 2-dimensional activation map of that filter. As a result, the network learns filters that activate per specific types of features at a given spatial position in the input.
This system can accurately identify images more than 90 percent of the time. Learn more about this project here.